Imperial College London


Faculty of EngineeringDepartment of Computing

Research Postgraduate



patrick.henriksen18 Website




CDT space, room 402Sherfield BuildingSouth Kensington Campus





Patrick Henriksen is a Ph.D. student in the Verification of Autonomous Systems (VAS) group at Imperial College London under the supervision of Prof. Alessio Lomuscio.  His research revolves around formal verification of neural networks. Patrick first got affiliated with the VAS group during his masters at Imperial College. In his MSc thesis, he proposed a novel method for verification of neural networks and implemented the method into a toolkit called VeriNet; a paper based on the thesis was later published at ECAI 2020. Building on VeriNet, Patrick published an improved algorithm at ICAJ 2021 and the implementation won second place in the Verification of Neural Networks Competition 2020. His current research focuses on further developing the VeriNet toolkit and related topics such as repair of neural networks.



Henriksen P, Leofante F, Lomuscio A, Repairing misclassifications in neural networks using limited data, SAC '22

Henriksen P, Hammernik K, Rueckert D, et al., Bias Field Robustness Verification of Large Neural Image Classifiers, British Machine Vision Conference (BMVC21)

Henriksen P, Lomuscio A, 2021, DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis, Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}, International Joint Conferences on Artificial Intelligence Organization

Henriksen P, Lomuscio A, Efficient Neural Network Verification via Adaptive Refinement and Adversarial Search, European Conference on Artificial Intelligence (ECAI20)

More Publications